72 votes
Accepted

How does an AI like ChatGPT answer a question in a subject which it may not know?

ChatGPT is a large language model. That means it's very good at stringing together words in ways that humans tend to use them. It's able to construct sentences that are grammatically correct and sound ...
Mithical's user avatar
  • 2,905
59 votes

Was ChatGPT trained on Stack Overflow data?

ChatGPT is in the Large Language Models (LLM) category. The most (in)famous GPT model is probably GPT-3, because since then, researchers realized that LLMs mostly follow a predictable scaling law, ...
Minh-Long Luu's user avatar
31 votes
Accepted

How does ChatGPT retain the context of previous questions?

Based on an answer by OpenAI, it appears that the illusion of understanding context is created by the model's capacity to accept very long input sequences. The OpenAI FAQ states that approximately ...
milez's user avatar
  • 981
27 votes

Why is ChatGPT bad at math?

chatGPT is able to create well-formed sentences which contain phrases that are fitting for the input. It has rules extracted from its data, but those are not rules of understanding, but rules of '...
gctwnl's user avatar
  • 371
20 votes

How does an AI like ChatGPT answer a question in a subject which it may not know?

ChatGPT does not actually know anything. But more importantly even, it does not know this fact! Hence, it does not know that it does not know. It is only good at combining text.
DrCommando's user avatar
19 votes
Accepted

Are Siri and Cortana AI programs?

Siri and Cortana are AI to some extent. The usual label is "weak AI" (also called "narrow" or "soft" AI). It turns out the Wikipedia article on Weak AI explicitly refers ...
Eric Platon's user avatar
  • 1,510
15 votes

How does an AI like ChatGPT answer a question in a subject which it may not know?

ChatGPT and other GPT-based machine learning models don't actually know anything in the sense you're thinking of. ChatGPT is a distant descendant of Markov chain text generators such as Dissociated ...
Mark's user avatar
  • 420
13 votes
Accepted

Why does ChatGPT create fake code?

ChatGPT is a generalised model. It does not understand any code. It does not know it is creating fake functions. It doesn't know that it isn't solving the question asked, because it doesn't know what ...
Rory Alsop's user avatar
11 votes

How does ChatGPT know math?

Adding on to txopen's answer, it is interesting to note that for larger numbers with similar digits ChatGPT is unable to make any useful distinctions. For instance: Me: Which number is bigger: 1234.12 ...
Milo Moses's user avatar
11 votes

Why is ChatGPT bad at math?

(Check out my heavily related answer to a similar question here) Why is ChatGPT bad at math, while it is very good at other stuff? The problem comes down to the age-old problem of learning vs ...
Robin van Hoorn's user avatar
10 votes

How does ChatGPT respond to novel prompts and commands?

Text continuation has the same reasons to work in any context, be it the middle of a sentence, after a question or after instructions. Following your example, the same word sequence could be a good ...
Jaume Oliver Lafont's user avatar
10 votes

How is ChatGPT able to repeat random numbers?

As well as decent modelling of purposes or strings of digits, ChatGPT can identify when a completely novel string might be a product name, a fictional person or place etc. The language model in ...
Neil Slater's user avatar
  • 32.1k
8 votes

Are Siri and Cortana AI programs?

I would classify both as having / using elements of AI, yes. But I wouldn't say either represents a truly "intelligent" (in the AGI sense) program. But here's the rub... as you'll see in other ...
mindcrime's user avatar
  • 3,757
8 votes
Accepted

How can you simulate level of curiosity for a chatbot?

It's possible to implement a form of curiosity-driven behavior without requiring full 'emotional intelligence'. One elementary strategy would be to define some form of similarity measure on inputs. ...
NietzscheanAI's user avatar
8 votes
Accepted

Are there any AI that have passed the MIST test so far?

Yes, although how useful this AI can be is another question entirely. mpgac is a "minimally intelligent AGI" trained on the GAC-80K corpus of MIST questions. As a result, it should be able to "...
Left SE On 10_6_19's user avatar
8 votes
Accepted

Which approaches could I use to create a simple chatbot using a neural network?

I would recommend to start by reading this blogpost. You can probably cannibalise the code to create a RNN that takes in one statement of a dialogue and then proceeds to output the answer to that ...
BlindKungFuMaster's user avatar
6 votes

Was the corruption of Microsoft's "Tay" chatbot an example of catastrophic forgetting?

Looking at what happened, it was something similar. Though, the case differs in my eyes from one perspective: if it could only do a few comedy jokes, that probably is not a profound starting point to ...
mico's user avatar
  • 937
6 votes

Was the corruption of Microsoft's "Tay" chatbot an example of catastrophic forgetting?

It was essentially a lack of control over crowd-sourced training data. While Tay was initially set up with some conversational ability, it seemed to be programmed to learn from interactions with ...
Oliver Mason's user avatar
  • 5,387
6 votes

How does ChatGPT know math?

I think that the dataset is so large and the model so well trained that it understood the probabilistic correlation of length in a token of numbers before a dot separation, and then the influence of ...
txopen's user avatar
  • 61
6 votes

OpenAI ChatGPT gives a network error at long responds. How can I fix it?

I resolved it by asking it to show me the first 10-20 lines, then the next 10 and so on until the end. In my case those were lines of code so it worked for me.
Danilo Bojanic's user avatar
6 votes
Accepted

How was ChatGPT trained?

The key ingredient is called Reinforcement Learning from Human Feedback (RLHF), that is having humans rate the model answers and use the feedback to guide the model training. The official blog ...
Rexcirus's user avatar
  • 1,174
5 votes
Accepted

How do chatbots work?

Chatterbots are used to communicate with a human and undergo conversations in such a way that the human which is communicating will think that he/she is talking to another human. There are two types ...
kiner_shah's user avatar
5 votes

What was the first machine that was able to carry on a conversation?

In 1986, the first PC therapist program was written by Joseph Weintraub. This program won the first Loebner Prize in 1991, and then again in 1992, 1993 and 1995. In 1981 or 1982, Jabberwacky was ...
wythagoras's user avatar
  • 1,521
5 votes
Accepted

Can I develop a chatbot to carry on a natural conversation with a human using NLP and neural networks?

I would not recommend using neural networks and NLP together to create a system sufficiently capable of conversation/dialogue that it would pass that current crop of Turing-like tests. Conversations ...
Oliver Mason's user avatar
  • 5,387
5 votes

Is "AIAngel" (Patreon) a fake?

No, AiAngel is not a bot. It's Rouge's software that changes his voice along with facial recognition software which tracks his movement and copies it to the avatar. That being said, he has created a ...
Ess Kay's user avatar
  • 151
5 votes

How does ChatGPT retain the context of previous questions?

Based on nothing but my own experience trying to build a similar chatbot using text-davinci-003, I think they are using the model itself to summarize the conversation, then feeding that summary back ...
RLC's user avatar
  • 214
5 votes

Why is ChatGPT not aware of panpsychism?

I tried this. The whole chat log is below: My input: Someone mentioned panpsychism to me, I don't know what it is. How do I find out? ChatGPT: Panpsychism is a philosophical theory that holds that ...
Neil Slater's user avatar
  • 32.1k
5 votes
Accepted

How could chatGPT avoid consuming what it produces

An effort to distinguish content from good content. One of the major complaints about ChatGPT (certainly you'll see this all over Stack Exchange sites) is that it tends to deliver low quality answers. ...
JamieB's user avatar
  • 166
4 votes
Accepted

Why was ELIZA able to induce "delusional thinking"?

I like your choice of "induce" instead of "produce," because the delusions came from the users. This means the answer has to do mostly with human psychology; people come equipped with lots of mental ...
Matthew Gray's user avatar
  • 4,262

Only top scored, non community-wiki answers of a minimum length are eligible